Fork me on GitHub

I am a senior research scientist at RISE Research institutes of Sweden heading The Deep Learning Research Group in Gothenburg. I have a PhD from Chalmers University of Technology, and I am the organizer of RISE Learning Machines Seminars.

I work on problems within applied AI where privacy, fairness, and efficiency is central. This includes work on federated learning, privacy-preserving representation learning, and generative adversarial netorks. The data modality varies, such as natural language, vision, and speech.

Some of our ongoing projects include The Federated Learning Testbed, The Swedish Medical Data Lab, AI Driven Financial Risk Assessment of Circular Business Models, and Smart Fire Detection.

Read more about me, or about my research group.

Publications

 
Federated learning using a mixture of experts

Arxiv 2020

 
Adversarial representation learning for private speech generation

Arxiv 2020

 
Adversarial representation learning for synthetic replacement of private attributes

Arxiv 2020

 
Semantic segmentation of fashion images using feature pyramid networks

CVCREATIVE 2019

 
Character-based recurrent neural networks for morphological relational reasoning

JLM 2019

 
C-RNN-GAN: Continuous recurrent neural networks with adversarial training

CML 2016

Recent talks

 
Learned representations and what they encode

2021-01-20

 
Social bias and fairness in NLP

2020-11-27

 
Uncertainty in deep learning

2020-11-05

Olof Mogren, PhD, RISE Research institutes of Sweden